View source on GitHub |
A general quantization scheme is being developed in tf.contrib.quantize
. (deprecated)
tf.compat.v1.train.do_quantize_training_on_graphdef(
input_graph, num_bits
)
Warning: THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: GraphDef quantized training rewriter is deprecated in the long term.
Consider using that instead, though since it is in the tf.contrib namespace, it is not subject to backward compatibility guarantees.
input_graph
: A GraphDef
.num_bits
: The number of bits for quantize training.The graph with quantize training done.